• 한국HCI학회:학술대회논문집
• /
• 2006.02a
• /
• pp.843-851
• /
• 2006

본 논문에서는 음성에 따른 얼굴 애니메이션을 사실적으로 표현하기 위한 조음기관(혀, 성대 등)의 움직임을 시각화하는 방법을 제시한다. 이를 위해서, 음성에 따른 얼굴 애니메이션을 위한 말뭉치(Corpus)를 생성하고, 생성된 말뭉치에 대해서 음소 단위의 분석(Phoneme alignment) 처리를 한 후, 각 음소에 따른 조음기관의 움직임을 생성한다. 본 논문에서는 조음기관의 움직임 생성을 위해서 얼굴 애니메이션 처리에서 널리 사용되고 있는 기저 모델 기반 형태 혼합 보간 기법(Blend shape Interpolation)을 사용하였다. 그리고 이를 통하여 프레임/키프레임 기반 움직임 생성 사용자 인터페이스를 구축하였다. 구축된 인터페이스를 통해 언어치료사가 직접 각 음소 별 조음기관의 정확한 모션 데이터를 생성토록 한다. 획득된 모션 데이터를 기반으로 각 음소 별 조음기관의 3차원 기본 기저를 모델링하고, 새롭게 입력된 음소 시퀀스(phoneme sequence)에 대해서 동기화된 3차원 조음기관의 움직임을 생성한다. 이를 통해 자연스러운 3차원 얼굴 애니메이션에 적용하여 얼굴과 동기화된 조음 기관의 움직임을 만들어 낼 수 있다.

• Proceedings of the KAIS Fall Conference
• /
• 2006.05a
• /
• pp.417-420
• /
• 2006

기존의 내용기반 비디오 검색 시스템들을 주석기반 검색 또는 특징기반 검색과 같은 단일 방식으로만 검색을 하므로 검색 효율이 낮을 뿐 아니라 완전한 자동 처리가 되지 않아 시스템 관리자나 주석자의 많은 노력을 요구한다. 본 논문에서는 주석기반 검색을 이용하여 대용량의 비디오 데이터에 대한 사용자의 다양한 의미검색을 지원하는 에이전트 기반에서의 자동화되고 통합된 비디오 의미기반 검색 시스템을 제안한다. 사용자의 기본적인 질의를 분석하고 질의에 의해 추출된 키 프레임의 이미지를 사용자가 선택함으로써 인덱싱 에이전트는 추출된 키 프레임의 주석에 대한 의미를 더욱 구체화시킨다.

• Journal of the Institute of Electronics Engineers of Korea TC
• /
• v.43 no.7 s.349
• /
• pp.14-23
• /
• 2006

Wireless Sensor Network(WSN) consists of huge number of sensor nodes which are small and inexpensive with very limited resources. The public key cryptography is undesirable to be used in WSN because of the limitations of the resources. A key management and predistribution techniques are required to apply the symmetric key cryptography in such a big network. Many key predistribution techniques and approaches have been proposed, but most of-them didn't consider the real WSN assumptions, In this paper, we propose a security framework that is based on a hierarchical grid for WSN considering the proper assumptions of the communication traffic and required connectivity. We apply simple keying material distribution scheme to measure the value of our framework. Finally, we provide security analysis for possible security threats in WSN.

• The KIPS Transactions:PartC
• /
• v.10C no.6
• /
• pp.769-778
• /
• 2003

XKMS(XML Key Management Specification), one of XML Security specification, defines the protocol for distributing and registering public keys for verifying digital signatures and enciphering XML documents of web service applications with various and complicate functions. In this paper, we propose XML Key Information protocol service model and implements reference model of protocol component based on standard specification. Also describes the analysis and security method of Key Information Service(XKIS) for Secure XML Web Service,paying attention to the features of XML based security service. This protocol component supported includes public key location by given identifier information, the binding of such keys to edentifier information. This reference model offers the security construction guideline for future domestric e-Business Frameworks.

• Journal of the Korea Society of Computer and Information
• /
• v.19 no.12
• /
• pp.197-207
• /
• 2014

In this paper, I propose an automatic extraction method of golf swing features using a practical TOF camera Kinect. I extracted 7 key swing frames and features using joints and depth information from a Kinect. I tested the proposed method on 50 swings from 10 players and showed the performace. It is meaningful that 3D swing features are extracted automatically using an inexpensive and simple system and specific numerical feature values can be used for the building of automatic swing analysis system.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2018.06a
• /
• pp.244-247
• /
• 2018

본 논문에서는 시니어를 위한 라이프 데이터 수집 및 행동분석 프레임 워크를 설명하고, 이의 부분적 구현을 자세히 설명한다. 본 연구는 시니어를 위한 라이프 데이터를 바탕으로 보호자가 없는 시니어를 보살핌과 동시에, 보호자가 미처 인지하지 못하는 시니어의 비정상적인 상태를 분석하여 판단하는 시스템을 연구한다. 먼저, 시니어가 시간을 많이 소요하는 TV 앞 상황을 가정하고, 방영되는 TV 콘텐츠와 TV 카메라를 이용한 시니어의 영상/음성 정보로 이상상태와 감정상태, TV 콘텐츠에 대한 반응과 반응속도를 체크한다. 구체적으로는 딥 러닝 기반의 API 와 멀티미디어 데이터 분석에서 사용되는 오픈 패키지를 바탕으로, 영상/음성의 키 프레임을 추출하여 감정 및 분위기를 분석하고 시니어의 얼굴 표정 인식, 행동 인식, 음성 인식을 수행한다.

• The Journal of Society for e-Business Studies
• /
• v.8 no.3
• /
• pp.241-257
• /
• 2003

XML is a global standard for the Internet and e-business, and its use is growing in proportion to the spreading speed of e-Commerce. Thus, a policy for providing more safe security service for exchanging e-documents within e-Commerce is necessary. XKMS, one of XML security specification, defines the protocol for distributing and registering public keys for verifying electronic signatures and enciphering e-documents of e-Commerce applications with various and complicate functions. In this paper, we propose X-KISS service reference model and implement service component based on standard specification. Also describes the analysis and security of XML key information service for safe e-Commerce, paying attention to the features of XML based security service. This reference model supported include public key location by given identifier information, the binding of such keys to identifier information. The client service component controls the number of locate threads and validate threads to analyze the minimum requirements of real-time key retrievals. This service modeling offers the security construction guideline for future domestic e-business frameworks.

• Journal of Digital Convergence
• /
• v.10 no.2
• /
• pp.217-223
• /
• 2012

By using the network, the robot can provide the anytime and anywhere various services. There is the advantage that it can provide the real time service by using the network description but the network robot has the network security vulnerability. Therefore, in the network robot environment, the authentication framework which can be satisfied the security function has to be established. In this paper, the security vulnerability which it can be generated in the network robot environment is analyze and the plan for reaction is prepared. And the authentication framework controlling the network robot safely was proposed.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.8 no.1
• /
• pp.50-59
• /
• 2007

In this paper, an anchor shot detection method, which is a basic technology for managing news videos for index and retrieval purposes is proposed. To do that, two most popular news program such as 'KBS 9 Hour News' and 'MBC 9 Hour News' are analyzed and 4-step rule based detection method is proposed First, in the preprocessing, video shot boundaries are detected and the 1st frame of each shot is extracted as a key frame. Then, the detected shot is declared as an anchor shot, if all the following 4 conditions are satisfied. 1) There is an anchor face in the key frame of a shot. 2) Spatial distribution of edges in the key frame is adequate. 3) Background color information of the key frame is similar to the color information of an anchor model. 4) Motion rate in the shot is low. In order to show the validity of the proposed method, three 'KBS 9 Hour News' and three 'MBC 9 Hour News', which have total running time of 108 in minute and are broadcasted at different days, are used for experiments. Average detection rates showed 0.97 in precision, 1.0 in recall, and 0.98 in F-measure.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2019.06a
• /
• pp.173-175
• /
• 2019

Animated images formats such as WebP are highly portable graphics formats that are being used everywhere on the Internet. Despite their small sizes and duration, WebP image previews the video without watching the entire content with minimum bandwidth. This paper proposed a novel method to generate personalized WebP images in the client side using its computation resources. The proposed system automatically extracts the WebP image from climax point using music analysis. Based on user interest, the system predicts the genre using Convolutional Neural Network (CNN). The proposed method can easily integrate with streaming platforms such as YouTube, Netflix, Hulu, and others.